Genetic Structural NAS: A Neural Network Architecture Search with Flexible Slot Connections
PROCEEDINGS OF THE 2023 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2023 COMPANION(2023)
摘要
Selecting an appropriate neural network architecture and hyperparameters to optimize performance for a given application is a difficult task. To overcome this challenge, Neural Architecture Search (NAS) and Hyperparameter Optimization (HPO) have been introduced. However, these techniques are often computationally-expensive and require significant amounts of execution time. To address this issue, we propose a semi-automated NAS approach that optimizes pre-existing architectural structures using genetic algorithms and eliminates unsuccessful combinations through shallow network training. The effectiveness of our technique was verified through an experiment that produces a family of AlexNet-like neural networks comprising 1296 models for image classification tasks. The computational study was conducted with five runs of a genetic algorithm, resulting in the deep models with mean loss of 0.7044 and accuracy of 0.7334, both with low standard deviations, outperforming the original AlexNet model with a significant margin.
更多查看译文
关键词
neural networks,genetic algorithm,neural architecture search
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要